HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation

TL;DR

HigherHRNet introduces a scale-aware, multi-resolution approach for bottom-up human pose estimation, significantly improving accuracy for small persons and crowded scenes by leveraging high-resolution feature pyramids.

Contribution

It proposes a novel scale-aware representation learning method with multi-resolution supervision and aggregation, advancing bottom-up pose estimation accuracy and robustness.

Findings

Outperforms previous methods by 2.5% AP on COCO for medium persons

Achieves 70.5% AP on COCO test-dev without post-processing

Surpasses top-down methods on CrowdPose test with 67.6% AP

Abstract

Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids. Equipped with multi-resolution supervision for training and multi-resolution aggregation for inference, the proposed approach is able to solve the scale variation challenge in bottom-up multi-person pose estimation and localize keypoints more precisely, especially for small person. The feature pyramid in HigherHRNet consists of feature map outputs from HRNet and upsampled higher-resolution outputs through a transposed convolution. HigherHRNet outperforms the previous best bottom-up method by 2.5% AP for medium person on COCO test-dev, showing its effectiveness in handling scale variation. Furthermore, HigherHRNet achieves new state-of-the-art result on COCO test-dev (70.5% AP) without using refinement or other post-processing techniques, surpassing all existing bottom-up methods. HigherHRNet even surpasses all top-down methods on CrowdPose test (67.6% AP), suggesting its robustness in crowded scene. The code and models are available at https://github.com/HRNet/Higher-HRNet-Human-Pose-Estimation.